Table of Contents

Search

  1. Preface
  2. Informatica Intelligent Cloud Services REST API
  3. Platform REST API version 2 resources
  4. Platform REST API version 3 resources
  5. Data Integration REST API
  6. File Ingestion and Replication REST API
  7. Streaming Ingestion and Replication REST API
  8. Model Serve REST API
  9. RunAJob utility
  10. ParamSetCli utility
  11. REST API codes
  12. REST API resource quick references

REST API Reference

REST API Reference

Creating a model deployment

Creating a model deployment

Use the Documents resource to create a model deployment.

POST request

To create a model deployment, include the project or folder ID in the URI. Use the following URI:
/frs/v1/Projects('<project ID>')/Documents
Include the following fields in the request:
Field
Type
Description
name
String
Model deployment name.
description
String
Optional. Description of the model deployment.
documentType
String
Use
MLOPS_DEPLOYMENT
.
documentState
String
Use an empty string.
nativeData
Object
Blob object that defines the model deployment.
Include the following fields in the nativeData object:
Field
Type
Description
name
String
Model deployment name.
modelId
String
ID of the machine learning model to associate with this deployment.
computeUnits
Integer
Maximum number of compute units that you want the model deployment to use. Enter a whole number that is a multiple of 4 from 4 to 40.

POST response

Returns the model deployment summary.
The following table describes the attributes in the model deployment summary:
Field
Description
id
ID of the model deployment.
name
Model deployment name.
description
Description of the model deployment.
owner
ID of the user who owns the deployment.
createdBy
ID of the user who created the deployment.
lastUpdatedBy
ID of the user who last edited the deployment.
lastAccessedBy
ID of the user who last viewed the deployment.
createdTime
Date and time that the deployment was created.
lastUpdatedTime
Date and time that the deployment was last edited.
lastAccessedTime
Date and time that the deployment was last viewed.
expiresBy
Date and time that the deployment will expire.
parentInfo
parentID
ID of the project or space that contains the deployment.
parentName
Name of the project or space that contains the deployment.
parentType
Type of object that contains the deployment.
documentType
contentType
documentState
aclRule
subcontainerCount
customAttributes
repoInfo

POST request example

The following example shows a request to create a model deployment:
POST <serverURL>//frs/v1/Projects('<deployment ID>')/Documents Content-Type: application/json Accept: application/json icSessionId: <SessionId> { "name": "dev1", "description": "desc", "documentType": "MLOPS_DEPLOYMENT", "documentState": "", "nativeData": { "documentBlob": "{\"name\":\"deployment1\",\"modelId\":\"01\",\"computeUnits\":4}" } }
You might receive a response similar to the following example:
{ "@odata.context": "$metadata#Documents", "id": "e1iwMxidbY2k2qS66uVpO7", "name": "ModelDeployment_test", "description": "", "owner": "7XFxlRShgWTdWswz0KZSYs", "createdBy": "7XFxlRShgWTdWswz0KZSYs", "lastUpdatedBy": "7XFxlRShgWTdWswz0KZSYs", "lastAccessedBy": "7XFxlRShgWTdWswz0KZSYs", "createdTime": "2023-09-14T20:51:01.074Z", "lastUpdatedTime": "2023-09-14T20:51:01.074Z", "lastAccessedTime": "2023-09-14T20:51:01.574Z", "expiresBy": "2038-01-18T00:00:00Z", "parentInfo": [ { "parentId": "7cCn5thwWFLhiZoSosphKL", "parentName": "REG", "parentType": "Space" }, { "parentId": "hPZoYnnVXMUcZY1lFvATm3", "parentName": "AK", "parentType": "Project" } ], "documentType": "MLOPS_DEPLOYMENT", "contentType": "Binary", "documentState": "VALID", "aclRule": "org", "subcontainerCount": 0, "customAttributes": null, "repoInfo": { "repoParams": [], "repoPath": null, "repoHandle": "e1iwMxidbY2k2qS66uVpO7", "frsPath": null }, "isSourceControlled": false, "checkedOutById": null }

0 COMMENTS

We’d like to hear from you!